Data Scientist RAG / NLP (English-Speaking)

Good Job! Good Life!

The HeadHunter Group is an innovative Staffing and Recruiting Company with HQ in US, Dover, Delaware, operating in Canada, Albania, Kosovo, Montenegro, North Macedonia, Bosnia & Herzegovina, Bulgaria, Serbia, Cyprus, Greece. We offer the newest mentality in Staffing industry and our core business are Candidates and Clients.

Job Overview:

Location: Prishtina

Type: Full-time

Department: AI / Data Science / Machine Learning

About the Role

We are seeking a highly motivated Data Scientist with hands-on experience in Retrieval-Augmented Generation (RAG) and natural language processing (NLP) to join our clients growing AI team. You will work at the intersection of data science, machine learning, and language models, building intelligent systems that retrieve, analyze, and generate human-like responses using large language models (LLMs).

Strong English communication skills are essential, as youll be collaborating with cross-functional teams and contributing to documentation, model evaluation, and client-facing insights.

Key Responsibilities

• Design, implement, and evaluate RAG pipelines combining retrieval systems (e.g., vector databases) and generative LLMs (e.g., GPT, LLaMA).
• Analyze large text corpora and structure them for effective indexing and retrieval (e.g., chunking, embedding strategies).

• Work with vector databases (e.g., FAISS, Pinecone, Weaviate, Qdrant) and tools like LangChain or LlamaIndex.

• Evaluate and optimize retrieval quality, generation accuracy, and latency.

• Collaborate with engineers, product managers, and designers to integrate RAG systems into real-world applications.

• Monitor performance metrics and fine-tune models to improve relevance, precision, and user satisfaction.

• Communicate technical concepts clearly in English both verbally and in writing (e.g., docs, presentations, demos).

Qualifications

• Proven experience as a Data Scientist, ML Engineer, or NLP specialist.

• Hands-on experience with RAG, semantic search, and LLM integration.

• Strong coding skills in Python and experience with transformers, Hugging Face, or OpenAI APIs.

• Proficient in NLP techniques: embedding models, similarity search, text chunking, etc.

• Comfortable with cloud tools (AWS, GCP, Azure), APIs, and MLOps workflows.

• Strong command of English (spoken and written).

• Bonus: Experience in multi-language RAG, fine-tuning, or evaluation frameworks like RAGAS or TruLens.

Note: Please note that only shortlisted candidates will be invited for an interview.

Our client offers equal opportunity for everyone, and no person shall be discriminated against on the grounds of age, gender, sexual orientation, disability, nationality, ethnic background, race, skin color, religion or ideology, political persuasion, social background or marital status.